Publications [Will update it when I get a chance]

Journals

[

Check out my Google Scholar Page for full list: Ruhi Sarikaya



[16] Y.B. Kim, K. Stratos, R. Sarikaya,  "A Framework for pre-training hidden-unit conditional random fields and its extension to long short term memory networks",  Computer Speech and Language, June 2017.


[9] R. Sarikaya, K. Kirchhoff, T. Shultze and D. Hakkani-Tur, “Processing Morphologically Rich Languages”, Guest Editorial, IEEE Trans. Audio Speech and Language Process., July, 2009.

 

[8] R. Sarikaya, A. Buyuktosunoglu, “A Unified Prediction Method for Predicting Program Behavior”, IEEE Transactions on Computers, vol. 59, no. 2, pp: 272-282, February 2010.

 

[7] R. Sarikaya, M. Afify, Y. Deng, H. Erdogan, Y. Gao, “Joint Morphological-Lexical Modeling for processing Morphologically-rich Languages”, IEEE Trans. Speech Audio Language Process.,  vol. 16, no. 7, pp. 1330-40, Sep. 2008.

 

[6] I. Zitouni, R. Sarikaya, Arabic Diacritic Restoration Using Maximum Entropy Models”, Computer Speech and Language. vol. 23, no. 3, pp: 257-276-, July 2009.

 

[5] R. Sarikaya,Rapid Bootstrapping of Statistical Spoken Dialog Systems”, Speech Communications vol. 50, no. 7, pp: 580-593, July 2008.

 

[4]  R. Sarikaya, Y. Gao, M. Picheny and Hakan Erdogan, “Semantic Confidence Measurement for Spoken Dialog Systems”, IEEE Trans. Speech and Audio Process, vol. 13, no. 4, July 2005.

 

[3] H. Erdogan, R. Sarikaya, S.F. Chen, Y. Gao and M. Picheny, Using Semantic Analysis to Improve Speech Recognition Performance”, Computer Speech & Language Journal, vol. 19 no:3 pp: 321-343,  July 2005

 

[2] B.L. Pellom, R. Sarikaya and J. H. L. Hansen , "Fast Likelihood Computation in Nearest-Neighbor Based Search for Continuous Speech Recognition",  IEEE Signal Processing Letters Journal, vol. 8, no 8, pp. 221-224, August, 2001.

 

[1] R. Sarikaya  and  J. H. L. Hansen,  "High Resolution Speech Feature Parameterization for Monophone Based Stressed Speech Recognition", IEEE  Signal Processing Letters Journal, vol. 7, no. 7, pp. 182-186, July, 2000.

 

Conferences

 
[94]  Y.B. Kim, S. Lee and R. Sarikaya, "Speaker-Sensitive Dual Memory Networks for Multi-Turn Slot Tagging", IEEE ASRU 2017, Okinawa, JP, December 2017.

[93]  J.K. Kim, Y.B. Kim, R. Sarikaya, and E. Fosler-Lussier, "Cross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources", EMNLP 2017, Copenhagen, Denmark, September 2017.

[45] R. Sarikaya, G. Hinton, B. Ramabhadran, "Deep Belief-Nets for Natural Language Call Routing", ICASSP-2011, Prague, Czech Republic, May 2011.
 
[44] R. Sarikaya, C. Isci, A. Buyuktosunoglu, “Run-time Workload Behavior Prediction Using Statistical Metric Modeling with Application to Dynamic Power Management”, IEEE  IISWC-2010, Atlanta, GA,  December 2010.
 

[43] R. Sarikaya, S. F. Chen, A. Sethy and B. Ramabhadran, “Impact of Word Classing on Shrinkage Based Exponential Models”, Interspeech-2010, Makuhari, Japan, Sept. 2010.

 

[42] R. Sarikaya, C. Isci and A. Buyuktosunoglu,  “Program Behavior Prediction Using a Statistical Metric Model”, ACM Sigmetrics, New York, NY, June 2010

 

[41] R. Sarikaya, A. Emami, M. Afify and B. Ramabhadran, “Continuous Space Language Modeling Techniques”, IEEE ICASSP-2010, Dallas, TX, March 2010.

 

[40] M. Afify and R. Sarikaya, “An Overview of Tied-Mixture Language Models”, 9th Conference on Language Engineering, Cairo, Egypt, December 2009 (invited paper).

 

[39] S. F. Chen, L. Mangu, B. Ramabhadran, R. Sarikaya, and A. Sethy, “Scaling Shrinkage-based Language Models",, IEEE ASRU-2009, December 2009, Merano, Italy.

 

[38] R. Sarikaya, D. Wang, S. Maskey, R. Zhang, E. E. Jan, B. Ramabhadran, S. Roukos, “Automatic Parallel data Extraction from Lightly Supervised Resources for MT”, Interspeech-2009, Brighton, England, Sept. 2009.

 

[37] R. Sarikaya, C. Isci and A. Buyuktosunoglu, “A Statistical Perspective for Computer Metric Modeling”, 7th Proactive Problem Prediction, Avoidance, and Diagnosis Conference, Yorktown Heights, NY,  April 2009.

 

[36] R. Sarikaya, M Afify, B. Kingsbury, “Tied-Mixture Language Models in Continuous Space”, HLT/NAACL-2009, Boulder, CO, June 2009.

 

[35] R. Sarikaya, Y. Deng, M Afify, B. Kingsbury and Y.Gao, “Machine Translation in Continuous Space”, Interspeech-2008, Brisbane, Australia, Sept. 2008.

 

[34] R. Sarikaya, A. Buyuktosunoglu, “Predicting Program Behavior Based On Objective function Minimization”,   IEEE International Symposium on Workload Characterization, IISWC-2007, Boston MA, Sept. 2007.

 

[33] R. Sarikaya, Y. Deng, and Y. Gao “Context-dependent Word modeling for SMT”, Antwerp, Belgium Interspeech-2007.

 

[32] R. Sarikaya, Y. Deng, “Joint Morphological-Lexical Language Modeling for Machine Translation”, HLT/NAACL-2007, Rochester NY April 2007.

 

[31] M. Afify, O. Siohan, and R. Sarikaya, “Gaussian Mixture Model Language Modeling”, ICASSP-2007 Honolulu, Hawaii, Sept. 2007.

 

[30] R. Sarikaya, M. Afify and Y. Gao, “Joint Language Modeling using Arabic Morphology”,  ICASSP-2007 Honolulu, Hawaii, Sept. 2007.

 

[29] R. Sarikaya, B. Zhou, D. Povey, M. Afify  and Y. Gao,  The Impact of ASR on the Speech-to-Speech Translation Performance”, Invited Paper, ICASSP-2007, Honolulu, Hawaii, Sept. 2007.

 

[28] Y. Gao, B. Zhou, L. Gu, R. Sarikaya, H-K. J. Kuo, M. Afify, W. Zhu, “IBM MASTOR: Multilingual Automatic Speech-to-speech Translator”, HLT Medical Speech Translation Workshop, NYC, June 2006.

 

[27] M. Afify, R. Sarikaya, H-K J. Kuo, L. Besacier, and Y. Gao,  On the Use of Morphological Analysis for Dialectal Arabic Speech Recognition”, Interspeech-2006,  Pittsburg PA, September 2006.

 

[26] I. Zitouni, J. Sorenson  and R. Sarikaya, “Feature Mining for Restoring Arabic Diacritics Using Maximum Entropy Approach”, ACL/Coling 2006, Sidney Australia, July 2006.

 

[25] R. Sarikaya, O. Emam,  I. Zitouni, Y. Gao, “Maximum Entropy Modeling for Vowelization of Arabic Text”,  Interspeech-2006, Pittsburg PA, September 2006.

 

[24] Y. Gao, B. Zhou, L. Gu, R. Sarikaya, H-K. J. Kuo, A. Rosti, M. Afify, W. Zhu, “IBM MASTOR: Multilingual Automatic Speech-to-speech Translator”, IEEE ICASSP, Toulouse France, May 2006.

 

[23] R. Sarikaya, H-K. J.  Kuo, Y. Gao, “Impact of Using Web Based Language Modeling on Speech Understanding”, IEEE ASRU 2005, San Juan Puerto Rico, December 2005.

 

[22] R. Sarikaya, H-K. J. Kuo V. Goel, and Y. Gao,”Exploiting Unlabeled Data Using Multiple Classifiers for Improved Natural Language Call-Routing ”,  Interspeech 2005, Lisbon Portugal, September 2005.

 

[21] R. Sarikaya, Agustin Gravano and Yuqing Gao, “Rapid Language Model Development Using External Resources for New Spoken Dialog Domains”, ICASSP-2005, Philadelphia, PA March 2005.

 

[20] R. Sarikaya, Y. Gao, and P. Virga, “Fast Semi-Automatic Semantic Annotation for Spoken Dialog Systems”, ICSLP-2004, Jeju Island South Korea, October 2004.

 

[19] R. Sarikaya, Yuqing Gao, and George Saon, “Fractional Fourier Transform Features for Speech Recognition”, ICASSP-2004, May 2004.

 

[18] R. Sarikaya, Y. Gao, M. Picheny, “A comparison of Rule-Based and Statistical Methods for Semantic Language Modeling and Confidence Measurement”, HLT/NAACL-2004,  May 2004.

 

[17] R. Sarikaya, Y. Gao, and M. Picheny, “Word Level Confidence Measurement Using Semantic Features”, International Conference on Acoustics Speech and Signal Processing  (ICASSP-2003),  Hong Kong, April 2003.

 

[16] J. Huang, B. Kingsbury, L. Mangu, G. Saon, R. Sarikaya and G. Zweig, "Improvements to the IBM Hub5e system", NIST RT'02 workshop presentation, 2002.

 

[15] H. Erdogan, R. Sarikaya, Y. Gao and M. Picheny, “Semantic Language Models  for Spoken Dialog Systems”, International Conference on Spoken  Language Processing (ICSLP-2002), September 2002, Denver, CO.

 

[14] Yuqing Gao, B. Zhou, Z. Diao, J. Sorensen, H. Erdogan, R. Sarikaya, F. Liu, M. Picheny, “A Trainable Approach for Multi-Lingual Speech-to-Speech Translation System”, Human Language Technologies (HLT-2002), San Diego, CA, March 2002.

 

[13] R. Sarikaya, Y. Gao, H. Erdogan and M. Picheny, “Turn-Based Language Modeling for Spoken Dialog Systems”, International Conference on Acoustics Speech and Signal Processing (ICASSP-2002), Orlando FL, May 2002.

 

[12] B. Kingsbury, G. Saon, L. Mangu, M. Padmanabhan, and R. Sarikaya,Robust Speech Recognition in Noisy Environments: The 2001 IBM Spine Evaluation System”, International Conference on Acoustics Speech and Signal Processing  (ICASSP-2002), Orlando FL, May 2002.

 

[11] U. Yapanel, J.H.L. Hansen, R. Sarikaya and B.L. Pellom , "Robust Digit Recognition in Noise: an Evaluation Using the AURORA Corpus",  European Conference on Speech Communication and Technology (Eurospeech-2001),  Aalborg, Denmark, September 2001. 

 

[10] R. Sarikaya and J. H. L. Hansen , "Analysis of the Root-Cepstrum for Acoustic Modeling and Fast Decoding", European Conference on Speech Communication and Technology (Eurospeech-2001),  Aalborg, Denmark, September 2001.

 

[9] J. H. L. Hansen, R. Sarikaya , U. Yapanel and B.L. Pellom, "Robust Speech Recognition in Noise: An Evaluation Using SPINE Corpus", European Conference on Speech Communication and Technology (Eurospeech-2001),  Aalborg, Denmark, September 2001.

 

[8] R. Sarikaya and J. H. L. Hansen , "Improved Jacobian Adaptation for Fast Acoustic Model Adaptation for Noisy Speech Recognition",  International Conference on Spoken Language Processing (ICSLP-2000), Beijing, China, vol. 3, pp. 702-705, October 2000.

 

[7] J. H. L. Hansen, B. Zhou, M. Akbacak, R. Sarikaya and B. Pellom "One Small Step for Man: Audio Stream Phrase Recognition for a National Gallery of the Spoken Word: A first Step",  International Conference on Spoken Language Processing  (ICSLP-2000), Beijing, China, vol. 3, pp. 1089-1092, October 2000.

 

[6] R. Sarikaya and J. H. L. Hansen , "PCA-PMC: A Novel Use of a priori Knowledge for Fast Parallel Model Combination",  IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP-2000), Istanbul, Turkey, vol. 2, pp. 1113-1116, June, 2000.

 

[5] R. Sarikaya  and  J. H. L. Hansen,, "Auditory Masking Threshold Estimation for Broadband Noise Sources with Application to Speech Enhancement ",  European Conference on Speech Communication and Technology (Eurospeech-99) , Budapest, Hungary, v. 6, pp. 2571-2574, September, 1999.

 

[4]  R. Sarikaya and J. H. L. Hansen , "Robust Speech Activity Detection in the Presence of Noise",  International Conference on Spoken Language Processing (ICSLP-98), Sydney,  Australia,  vol.4,  pp. 1455-1458,  November 1998.

 

[3]  R. Sarikaya, B.L. Pellom, and J.H.L. Hansen, "Wavelet Packet Transform Features with Application to Speaker Identification",, IEEE Nordic Signal Processing Symposium (NORSIG-98), Vigso, Denmark,  pp. 81-84, June, 1998.

 

[2]  R. Sarikaya  and   J.N. Gowdy, "Subband Based Classification of Speech Under Stress",  IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP-98), Seattle, WA, vol. 1, pp. 569-572,  May, 1998.

 

[1] R. Sarikaya  and   J.N. Gowdy, "Wavelet Based Analysis of Speech Under  Stress", IEEE Southeastcon, Blacksburg, Virginia, vol.1, pp. 92-96,  April, 1997.

 
Ċ
Ruhi Sarikaya,
Feb 8, 2011, 6:38 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 8:21 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 8:35 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 8:18 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 8:32 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 8:33 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 8:28 AM
Ċ
Ruhi Sarikaya,
Feb 7, 2011, 12:50 PM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 11:50 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 7:18 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 8:25 AM
Ċ
Ruhi Sarikaya,
Aug 25, 2017, 5:03 PM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 11:53 AM
Ċ
cdwm.pdf
(153k)
Ruhi Sarikaya,
Feb 7, 2011, 12:54 PM
Ċ
Ruhi Sarikaya,
Nov 23, 2017, 12:15 PM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 8:30 AM
Ċ
Ruhi Sarikaya,
Feb 7, 2011, 12:40 PM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 11:46 AM
Ċ
Ruhi Sarikaya,
Feb 6, 2011, 11:32 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 10:58 AM
Ċ
Ruhi Sarikaya,
Feb 7, 2011, 1:03 PM
Ċ
Ruhi Sarikaya,
Feb 7, 2011, 12:59 PM
ċ
Ruhi Sarikaya,
Feb 6, 2011, 11:20 AM
Ċ
Ruhi Sarikaya,
Feb 7, 2011, 1:03 PM
ċ
Ruhi Sarikaya,
Feb 5, 2011, 11:00 AM
ċ
Ruhi Sarikaya,
Feb 5, 2011, 11:01 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 10:46 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 10:50 AM
Ċ
Ruhi Sarikaya,
Feb 7, 2011, 1:11 PM
Ċ
Ruhi Sarikaya,
Feb 7, 2011, 1:09 PM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 7:47 AM
ċ
Ruhi Sarikaya,
Feb 6, 2011, 11:45 AM
Ċ
Ruhi Sarikaya,
Feb 6, 2011, 11:27 AM
Ċ
Ruhi Sarikaya,
Feb 6, 2011, 11:25 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 10:52 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 11:55 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 7:32 AM
Ċ
Ruhi Sarikaya,
Feb 6, 2011, 11:30 AM
Ċ
Ruhi Sarikaya,
Feb 6, 2011, 11:28 AM
Ċ
Ruhi Sarikaya,
Feb 6, 2011, 5:58 PM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 7:38 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 10:44 AM
Ċ
Ruhi Sarikaya,
Feb 8, 2011, 6:40 AM
ċ
norsig.ps
(323k)
Ruhi Sarikaya,
Feb 6, 2011, 11:41 AM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 7:44 AM
Ċ
Ruhi Sarikaya,
Nov 23, 2017, 12:03 PM
Ċ
Ruhi Sarikaya,
Feb 5, 2011, 8:13 AM
Comments